In [ ]:
# Mover modelo a dispositivo GPU si está disponible
def get_default_device():
if torch.cuda.is_available():
return torch.device('cuda')
else:
return torch.device('cpu')
def to_device(data, device):
if isinstance(data, (list,tuple)):
return [to_device(x, device) for x in data]
return data.to(device, non_blocking=True)
class DeviceDataLoader():
def __init__(self, dl, device):
self.dl = dl
self.device = device
def __iter__(self):
for b in self.dl:
yield to_device(b, self.device)
def __len__(self):
return len(self.dl)
device = get_default_device()
train_dl = DeviceDataLoader(train_dl, device)
val_dl = DeviceDataLoader(val_dl, device)
test_dl = DeviceDataLoader(test_dl, device)
model = ResNet()
model = to_device(model, device)
@torch.no_grad()
def evaluate(model, val_loader):
model.eval()
outputs = [model.validation_step(batch) for batch in val_loader]
return model.validation_epoch_end(outputs)
def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
history = []
optimizer = opt_func(model.parameters(), lr)
for epoch in range(epochs):
model.train()
train_losses = []
for batch in train_loader:
loss = model.training_step(batch)
train_losses.append(loss)
loss.backward()
optimizer.step()
optimizer.zero_grad()
result = evaluate(model, val_loader)
result['train_loss'] = torch.stack(train_losses).mean().item()
model.epoch_end(epoch, result)
history.append(result)
return history
# Configuración de hiperparámetros y entrenamiento
num_epochs = 8
opt_func = torch.optim.Adam
lr = 5.5e-5
history = fit(num_epochs, lr, model, train_dl, val_dl, opt_func)
# Guardar el modelo entrenado
model_path = "resnet50_garbage_classification.pth"
torch.save(model.state_dict(), model_path)
print(f"Modelo guardado en {model_path}")
# Graficar precisión y pérdida
import matplotlib.pyplot as plt
def plot_accuracies(history):
accuracies = [x['val_acc'] for x in history]
plt.plot(accuracies, '-x')
plt.xlabel('epoch')
plt.ylabel('accuracy')
plt.title('Accuracy vs. No. of epochs')
plot_accuracies(history)
def plot_losses(history):
train_losses = [x.get('train_loss') for x in history]
val_losses = [x['val_loss'] for x in history]
plt.plot(train_losses, '-bx')
plt.plot(val_losses, '-rx')
plt.xlabel('epoch')
plt.ylabel('loss')
plt.legend(['Training', 'Validation'])
plt.title('Loss vs. No. of epochs')
plot_losses(history)
/usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet50_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet50_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) Downloading: "https://download.pytorch.org/models/resnet50-0676ba61.pth" to /root/.cache/torch/hub/checkpoints/resnet50-0676ba61.pth 100%|██████████| 97.8M/97.8M [00:00<00:00, 134MB/s]
Epoch 1: train_loss: 0.3769, val_loss: 0.1374, val_acc: 0.9567 Epoch 2: train_loss: 0.0808, val_loss: 0.1102, val_acc: 0.9706 Epoch 3: train_loss: 0.0422, val_loss: 0.0980, val_acc: 0.9731 Epoch 4: train_loss: 0.0370, val_loss: 0.1108, val_acc: 0.9711 Epoch 5: train_loss: 0.0294, val_loss: 0.0858, val_acc: 0.9756 Epoch 6: train_loss: 0.0343, val_loss: 0.1051, val_acc: 0.9730 Epoch 7: train_loss: 0.0185, val_loss: 0.1216, val_acc: 0.9673 Epoch 8: train_loss: 0.0264, val_loss: 0.1119, val_acc: 0.9748 Modelo guardado en resnet50_garbage_classification.pth
